NYC
skills/vm0-ai/vm0-skills/twenty/Gen Agent Trust Hub

twenty

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The skill utilizes bash -c to execute curl commands. While this is used to work around environment variable handling issues in specific environments, it increases the complexity of command parsing and requires the agent to correctly interpolate variables like {companyId} and {personId}.
  • [Indirect Prompt Injection] (LOW): The skill retrieves and processes data from an external CRM API, which could contain attacker-controlled content designed to influence the agent's behavior. Ingestion points: REST and GraphQL API responses from TWENTY_API_URL (specifically fields for companies, people, notes, and tasks). Boundary markers: None. Capability inventory: Subprocess calls involving curl, bash, and jq. Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM